dsh-think-any-lang
Run the following command in DeepSeek Harness:
dsh plugin install lco117/dsh-think-any-lang
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command dsh plugin install lco117/dsh-think-any-lang, or visit the GitHub repository at https://github.com/lco117/dsh-think-any-lang for detailed installation instructions.
About this plugin
In AI model reasoning, users often face a language dilemma: they want the model to think deeply in a specific language for better results, yet the final reply needs to remain in the user's language for clarity. The dsh-think-any-lang plugin addresses this issue by adding a 'Thinking Language' dropdown in the DeepSeek Harness settings interface, allowing users to choose the language for model reasoning, with support for multiple languages like Chinese, English, Japanese, and more.
Its core capability lies in efficient implementation: through system prompt instructions, it enables zero-latency and zero-extra-call experiences, while user settings are persisted and survive restarts. This plugin is ideal for all users of DeepSeek Harness, including developers, researchers, and general users, especially in multilingual contexts or language-specific tasks, where it can significantly enhance workflow and interaction.
Screenshots
Use Cases
- Users want the model to reason in a specific language for improved accuracy.
- In multilingual project collaborations, ensure the model's internal reasoning aligns with team language needs.
- For testing or comparing the model's reasoning performance and efficiency across languages.
Best For
- Developers: Technical personnel who need to customize the reasoning language of DeepSeek Harness models.
- Researchers: Scholars or scientists studying multilingual AI reasoning capabilities.
- Multilingual Users: Users who want the model to think in a specific language for daily communication or work.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.